{"id":"W4366599818","doi":"10.17323/jle.2023.11045","title":"Automated Measures of Lexical Sophistication: Predicting Proficiency in an Integrated Academic Writing Task","year":2023,"lang":"en","type":"article","venue":"Journal of language and Education","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Waseda University","keywords":"Fluency; Sophistication; Computer science; Task (project management); Variance (accounting); Lexical diversity; Natural language processing; Language proficiency; Artificial intelligence; Second language writing; Psychology; Linguistics; Mathematics education; Vocabulary; Second language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009140156,0.00006188157,0.0001363181,0.0003804981,0.00004024935,0.00001584246,0.00009037168,0.00008947837,0.0005620421],"category_scores_gemma":[0.0003572525,0.00005349135,0.0000251196,0.0004254746,0.0000318667,0.0001650825,0.0000084619,0.0003147864,0.000008171325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002749272,"about_ca_system_score_gemma":0.0001195505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000620939,"about_ca_topic_score_gemma":0.000003076164,"domain_scores_codex":[0.9990174,0.0001740443,0.0004515911,0.00009967416,0.0001332859,0.0001240599],"domain_scores_gemma":[0.9993166,0.00009860907,0.0003000994,0.00008314598,0.0001397729,0.00006182178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002289876,0.0005500644,0.1422533,0.0001405363,0.00006284381,0.0001372086,0.3428484,0.000151457,0.08395758,0.001408245,0.003875495,0.4243859],"study_design_scores_gemma":[0.0006723765,0.0002655765,0.6534982,0.0003405449,0.0000384796,0.0003034181,0.3408874,0.002918006,0.0005729162,0.0001249972,0.0002449706,0.0001330878],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9952875,0.003328184,0.00009766289,0.0002507831,0.0003089739,0.0000660673,0.000002035276,0.00005577401,0.0006029977],"genre_scores_gemma":[0.9990603,0.00001468013,0.0001902034,0.0002526384,0.0003093262,0.000004917232,0.00002559759,0.000008402554,0.0001339693],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.511245,"threshold_uncertainty_score":0.6153966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04037119491325712,"score_gpt":0.3951687748602904,"score_spread":0.3547975799470333,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}